检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Gao, Shiqi Gong, Tianxiang Lin, Zijie Xu, Runhua Zhou, Haoyi Li, Jianxin SKLCCSE School of Computer Science and Engineering Beihang University China School of Software Beihang University China National University of Singapore Singapore Zhongguancun Laboratory Beijing China

ISBN: (纸本)157735897X

Uncertainty estimation is essential for practical applications such as decision-making, risk assessment, and human-AI collaboration. However, uncertainty estimation in open-ended question-answering (QA) tasks presents unique challenges. The output space for open-ended QA is vast and discrete, and the autoregressive nature of LLMs, combined with the rapid increase in model parameters, makes inference sampling significantly costly. An ideal uncertainty estimation for LLMs should meet two criteria: 1) incur no additional inference cost and 2) capture the semantic dependencies of token-level uncertainty within sequences. We propose a promising solution that converts redundancy into randomness in the extensive parameters of LLMs to quantify knowledge uncertainty. We can obtain token-level Monte Carlo samples without multiple inferences by introducing randomness during a single forward pass. We theoretically analyze the FLUE sampling method and employ a post-processing method to learn the state transitions from token uncertainty to sequence uncertainty. In open-ended QA tasks, we demonstrate that FLUE can achieve competitive performance in estimating the uncertainty of generated sentences without extra inference overhead. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Multi-cost fusion stereo matching algorithm based on guided filter aggregation 3

Multi-cost fusion stereo matching algorithm based on guided ...

引用

3rd International Conference on Artificial Intelligence and computer engineering, ICAICE 2022

作者： Liu, Jingwen Zhang, Xuedong School of Computer and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China

ISBN: (纸本)9781510663473

Aiming at the low matching accuracy of existing local stereo matching algorithms in weak texture areas, a local stereo matching algorithm based on multi-matching cost fusion and guided filtering cost aggregation with adaptive parameters is proposed. First, use the gradient direction to improve the gradient cost, and calculate the matching cost by combining the gradient cost with the Census transform and color cost. Secondly, the cost is aggregated by the guided filtering of adaptive parameters;Finally, the final disparity map is obtained through disparity calculation and multi-step disparity refinement. The improved algorithm is tested on 15 training sets on the Middlebury3 platform, and the average false matching rates of bad4.0 in all areas and non-occluded areas are 19.9% and 13.2%, respectively, which is improved compared with AD-Census and other algorithms. © 2023 SPIE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Extracting Driving Styles from Automotive Sensor Data to Develop Personas 9

Extracting Driving Styles from Automotive Sensor Data to Dev...

引用

9th International Conference on computer science and engineering, UBMK 2024

作者： Kaya, M. Cagri Bouraffa, Tayssir Wnuk, Krzysztof Chalmers University of Technology University of Gothenburg Department of Computer Science and Engineering GothenburgSE-41296 Sweden Blekinge Institute of Technology Department of Software Engineering KarlskronaSE-37179 Sweden

ISBN: (纸本)9798350365887

Creating accurate and insightful personas for automotive applications requires understanding the diverse driving styles that emerge from sensor data. This paper introduces initial results of our methodology for developing personas based on the analysis of automotive sensor data, which captures various driving behaviors. We present a comprehensive process that begins with the extraction of driving events from sensor data, followed by the identification of distinct driving styles through K-Means clustering. Our approach is innovative in its use of dynamic, real-world driving data as opposed to static or direct user interaction data commonly employed in persona development. This allows for a deeper understanding of driver behaviors, which are indirectly inferred from sensor data, thus providing a foundation for creating detailed personas. © 2024 IEEE.

关键词： Automotive sensor data clustering driving styles event detection persona development

来源：评论

学校读者我要写书评

暂无评论

YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment 41st

YFLM: An Improved Levenberg-Marquardt Algorithm for Global ...

引用

41st computer Graphics International Conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

A Concept Drift Tolerant Abnormal Detection Method for Network Traffic 15

A Concept Drift Tolerant Abnormal Detection Method for Netwo...

引用

15th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2023

作者： Wang, Xu Han, Li Sun, Shimin Xu, Guowei Tianjin University of Technology National Engineering Laboratory for Computer Virus Prevention and Control Technology School of Computer Science and Engineering Tianjin China Tiangong University School of Software Tianjin China

ISBN: (纸本)9798350308693

we propose a cutting-edge solution that leverages passive adaptive methods based on ensemble learning to effectively detect anomalous traffic in data streams. Our approach tackles the issue of concept drift by integrating various deep learning models, each offering a unique perspective to learn data features. By doing so, our solution can accurately capture the distribution of data concepts and propose weight layers to make the model adaptable to changes caused by concept drift. In a series of experiments conducted on public datasets, our model demonstrated remarkable effectiveness in detecting anomalies, achieving accuracy rates of over 97% after adapting to concept drift. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Learning Two-factor Representation for Magnetic Resonance Image Super-resolution

Learning Two-factor Representation for Magnetic Resonance Im...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Weifeng Chen, Heng Su, Pengxiang School of Information Engineering Nanchang University Nanchang China School of Mathematics and Computer Science Nanchang University Nanchang China School of Software Nanchang University Nanchang China

ISBN: (纸本)9798350368741

Magnetic Resonance Imaging (MRI) requires a trade-off between resolution, signal-to-noise ratio, and scan time, making high-resolution (HR) acquisition challenging. Therefore, super-resolution for MR image is a feasible solution. However, most existing methods face challenges in accurately learning a continuous volumetric representation from low-resolution image or require HR image for supervision. To solve these challenges, we propose a novel method for MR image super-resolution based on two-factor representation. Specifically, we factorize intensity signals into a linear combination of learnable basis and coefficient factors, enabling efficient continuous volumetric representation from low-resolution MR image. Besides, we introduce a coordinate-based encoding to capture structural relationships between sparse voxels, facilitating smooth completion in unobserved regions. Experiments on BraTS 2019 and MSSEG 2016 datasets demonstrate that our method achieves state-of-the-art performance, providing superior visual fidelity and robustness, particularly in large up-sampling scale MR image super-resolution. © 2025 IEEE.

关键词： Coordinate-based encoding MR image super-resolution Two-factor representation

来源：评论

学校读者我要写书评

暂无评论

Research to Practice of Blended Learning in computer Programming Course 53

Research to Practice of Blended Learning in Computer Program...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Zhang, Liang Chen, Tianyi Zong, Yue Zhang, Lijun School of Computer Science and Engineering Beihang University Beijing China School of Aeronautic Science and Engineering Beihang University Beijing China School of Software Beihang University Beijing China

ISBN: (纸本)9798350336429

This research to practice WIP paper presented a Blended Learning (BL) approach to teaching Data Structures and Programming in Python (DSPP) course. This approach increased students' learning engagement, academic performance, and course satisfaction. There is an intense need to study the BL approach in higher education, especially during the COVID-19 epidemic. Although BL pedagogy has achieved great success in college, there needs to be more quantitative research and practice in the computer programming course. This paper takes the DSPP course as an example to introduce the BL approach in detail. First, we designed the BL process for the computer programming course, which includes specific pre-class, in-class, and after-class activities. Second, we divide a course's knowledge and BL activities into remember, understand, apply, analyze, evaluate, and create levels according to Bloom's Taxonomy. So the knowledge and activities can be corresponding according to the cognitive level. We take a chapter in the DSPP course as an example to introduce it in detail. Third, to support the efficient implementation of BL activities, we have designed and developed several online learning systems, including an Online Judge system (OJ), Question&Anwser website (Q&A), and Peer Review Studio (PRS). To assess the effectiveness of the BL approach, we conducted the study at the DSPP course for undergraduate students in 2021 and 2023. In 2021, we taught the DSPP course in traditional pedagogy. In 2023, we began to implement BL pedagogy. By analyzing students' learning data, we compared the effect of the two pedagogy. We use the nonparametric independent-samples Kruskal-Wallis test to measure the changes in learning engagement, course performance, and student satisfaction. The results show that they were significantly improved in 2022. The course questionnaire of 2022 shows that most students prefer the BL approach. © 2023 IEEE.

关键词： Active Learning Blended Learning Bloom's Taxonomy computer programming Online Learning System

来源：评论

学校读者我要写书评

暂无评论

3WOS: Finding the Pillars of Strength in Three-Way Oversampling with Density Clustering for Imbalanced Data Synthesis 11th

3WOS: Finding the Pillars of Strength in Three-Way Oversa...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Fang, Yu Li, Tianrui Min, Fan School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China

ISBN: (纸本)9783031927409

In tackling the issues of overfitting and limited generalization in machine learning models, especially with imbalanced and limited data, oversampling methods have been widely used to enhance model discrimination by generating synthetic minority samples. However, these methods often struggle to capture the expressive nuances of the minority class due to noisy interference. In response to this challenge, we propose a three-way oversampling (3WOS) method that partitions data into three regions via density clustering, then synthesizes samples in purified regions to avoid noise. The 3WOS operates in two stages: first, a three-way density clustering (3WDC) process uses density ratios to divide data and identify the FringeRegion (Fr) as a source of benchmark representative samples, aiding in similar data recognition and noise mitigation. Second, a data synthesis strategy creates a purified region from the representative samples, where the FringeRegion provides meaningful, discriminative data for synthesis through linear interpolation. This approach avoids data redundancy and overlap, ensuring a more robust minority representation. Extensive experiments validate 3WOS effectiveness, demonstrating significant improvements in model performance, particularly in enhancing minority class representation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

引用

computer Modeling in engineering & sciences 2024年第3期138卷 3013-3032页

作者： Chunlin Xiong Zhengqiu Weng Jia Liu Liang Gu Fayez Alqahtani Amr Gafar Pradip Kumar Sharma Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518052China Sangfor Technologies Inc. Shenzhen518055China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou325035China College of Computer Science&Technology Zhejiang University of TechnologyHangzhou310023China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Math&Computer Science Department Faculty of ScienceMenofia UniversityShebin El-KomEgypt Computing Science Department University of AberdeenAberdeenUK

With the development of hardware devices and the upgrading of smartphones,a large number of users save privacy-related information in mobile devices,mainly smartphones,which puts forward higher demands on the protection of mobile users’privacy *** present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of high precision and non-perception,but there are still shortcomings such as low data collection efficiency,untrustworthy participating nodes,and lack of *** this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and federated learning to improve the data collection efficiency of mobile user authentication,reduce the probability of the model being bypassed by attackers,and reduce the overhead of data centralized processing and the risk of privacy leakage;(2)Use certificateless encryption to realize the authentication of the device to ensure the credibility of the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of mobile devices to improve the accuracy of model *** experimental results on the real environment dataset of 1513 people show that themethod proposed in this paper can effectively resist poisoning attacks while ensuring the accuracy and efficiency of mobile user authentication.

关键词： Mobile authentication blockchain federated learning smart contract certificateless encryption VMD LSTM

来源：评论

学校读者我要写书评

暂无评论

EEiF: Efficient Isolated Forest with e Branches for Anomaly Detection 24

EEiF: Efficient Isolated Forest with e Branches for Anomaly ...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhang, Yifan Xiang, Haolong Zhang, Xuyun Xu, Xiaolong Fan, Wei Zhang, Qin Qi, Lianyong School of Software Nanjing University of Information Science and Technology China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services China School of Computing Macquarie University Australia University of Oxford Uffield Department of Women's & Reproductive Health United Kingdom College of Computer Science and Software Engineering Shenzhen University China Faculty of Science and Engineering China

ISBN: (纸本)9798331506681

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods. © 2024 IEEE.

关键词： Anomaly Detection Efficient FR clustering Parallel Algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：